ML Anthology

Probabilistic Planning with Risk-Sensitive Criterion

Ping Hou
IJCAI 2016 pp. 3996-3997
/ijcai/2016/hou2016ijcai-probabilistic/

Abstract

While probabilistic planning have been extensively studied by artificial intelligence communities for planning under uncertainty, the objective to minimize the expected cumulative cost is inappropriate for high-stake planning problems. With this motivation in mind, we revisit the Risk-Sensitive criterion (RS-criterion), where the objective is to find a policy that maximizes the probability that the cumulative cost is within some user-defined cost threshold. By combining goal-directed MDPs and POMDPs with the RS-criterion, the corresponding risk-sensitive probabilistic planning models —Risk-Sensitive MDPs (RS-MDPs) and Risk-Sensitive POMDPs (RS-POMDPs) — can be formalized. The overall scope of this research is to develop efficient and scalable RS-MDP and RS-POMDP algorithms. PDF

PDF IJCAI Semantic Scholar

Cite

Text

Hou. "Probabilistic Planning with Risk-Sensitive Criterion." International Joint Conference on Artificial Intelligence, 2016.

Markdown

[Hou. "Probabilistic Planning with Risk-Sensitive Criterion." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/hou2016ijcai-probabilistic/)

BibTeX

@inproceedings{hou2016ijcai-probabilistic,
  title     = {{Probabilistic Planning with Risk-Sensitive Criterion}},
  author    = {Hou, Ping},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {3996-3997},
  url       = {https://mlanthology.org/ijcai/2016/hou2016ijcai-probabilistic/}
}